java href_java读取html文件并抽取a href相关连接和链接标题

import java.util.regex.Matcher;

import java.util.regex.Pattern;

import java.util.*;

import java.io.*;

import java.nio.CharBuffer;

public class RegTest

{

public static void main(String[] args)

{

//定义一个文章列表类。包含文章的网址和文章标题

class ArticleList{

String URLs;

String title;

public ArticleList(){}

public ArticleList(String t,String u)

{

title=t;

URLs=u;

}

public String toString()

{

return ("标题："+title+" 网址："+URLs+" ");

}

}

//----------start---读取HTML文件至buff--------------------------------------------------------

File file = new File("C://bb.html");

BufferedReader reader = null;

StringBuffer buff = new StringBuffer();

try {

System.out.println("以行为单位读取文件内容，一次读一整行：");

reader = new BufferedReader(new FileReader(file));

String tempString = null;

int line = 1;

//一次读入一行，直到读入null为文件结束

while ((tempString = reader.readLine()) != null){

//显示行号

buff.append(tempString+"/r/n");

//System.out.println("line " + line + ": " + tempString);

line++;

}

// System.out.println(buff.toString());

reader.close();

} catch (IOException e) {

e.printStackTrace();

} finally {

if (reader != null){

try {

reader.close();

} catch (IOException e1) {

}

}

}

//------------end--读取---------------------------------------------------------------------------

ArrayList al=new ArrayList();

String s=buff.toString();

System.out.println(s);//"

企业推广 | 搜索风云榜 | 关于百度 | About Baidu

©2008 Baidu 使用百度前必读 京ICP证030173号